© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51850
    Prev
    Next
    INDEX
    Explanations

    sought, rought, brought, bought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§Ķ书记
    -0.13
    ITY
    -0.12
    ity
    -0.11
    hed
    -0.10
    otta
    -0.10
    ä¸įè´Ł
    -0.10
    Ùħا
    -0.10
    ature
    -0.09
    hop
    -0.09
    rtype
    -0.09
    POSITIVE LOGITS
    ype
    0.13
    est
    0.13
    åĵĩ
    0.13
    sWith
    0.13
    iful
    0.12
    ãĤ¥
    0.12
    ting
    0.12
    serrat
    0.12
    ters
    0.11
    ted
    0.11
    Activations Density 0.023%

    No Known Activations